Yuan Zhang

papers

1,343

total citations

papers (17)

Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation

ICCV 2023arXiv

420

citations

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

ICML 2025arXiv

214

citations

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

CVPR 2020arXiv

134

citations

MobRecon: Mobile-Friendly Hand Mesh Reconstruction From Monocular Image

CVPR 2022arXiv

123

citations

RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

CVPR 2025arXiv

citations

Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets

ECCV 2020arXiv

citations

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

NEURIPS 2025arXiv

citations

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

CVPR 2025arXiv

citations

Cloud-Device Collaborative Learning for Multimodal Large Language Models

CVPR 2024arXiv

citations

DLF: Extreme Image Compression with Dual-generative Latent Fusion

ICCV 2025arXiv

citations

Open Ad Hoc Teamwork with Cooperative Game Theory

ICML 2024arXiv

citations

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

AAAI 2025arXiv

citations

Enhancing the Power of OOD Detection via Sample-Aware Model Selection

CVPR 2024

citations

Yuan Zhang

papers (17)

Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

MobRecon: Mobile-Friendly Hand Mesh Reconstruction From Monocular Image

RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Knowledge Diffusion for Distillation

DVIS: Decoupled Video Instance Segmentation Framework

FreeKD: Knowledge Distillation via Semantic Frequency Prompt

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Cloud-Device Collaborative Learning for Multimodal Large Language Models

DLF: Extreme Image Compression with Dual-generative Latent Fusion

Open Ad Hoc Teamwork with Cooperative Game Theory

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Enhancing the Power of OOD Detection via Sample-Aware Model Selection

papers (17)

Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

MobRecon: Mobile-Friendly Hand Mesh Reconstruction From Monocular Image

RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Knowledge Diffusion for Distillation

DVIS: Decoupled Video Instance Segmentation Framework

FreeKD: Knowledge Distillation via Semantic Frequency Prompt

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Cloud-Device Collaborative Learning for Multimodal Large Language Models

DLF: Extreme Image Compression with Dual-generative Latent Fusion

Open Ad Hoc Teamwork with Cooperative Game Theory

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Enhancing the Power of OOD Detection via Sample-Aware Model Selection